8af477fca8
Changes to be committed: - kleinere Korrekturen/Verbesserungen modified: homepage/redesign2018/markdownExperiment/Makefile modified: homepage/redesign2018/markdownExperiment/src/jsonSd/cwsvJudo.json - Neuer Ansatz für den Wettkampfsammler new file: wkOrg/src/wkScraper/scrapyDocAuthorSpider.py new file: wkOrg/src/wkScraper/scrapyDocQuoteSpider.py new file: wkOrg/src/wkScraper/scrapyJvsKalender.py
23 lines
620 B
Python
23 lines
620 B
Python
#!/usr/bin/env python
|
|
# -*- coding: UTF-8 -*-
|
|
|
|
import scrapy
|
|
|
|
|
|
class QuotesSpider(scrapy.Spider):
|
|
name = "quotes"
|
|
start_urls = [
|
|
'http://quotes.toscrape.com/tag/humor/',
|
|
]
|
|
|
|
def parse(self, response):
|
|
for quote in response.css('div.quote'):
|
|
yield {
|
|
'text': quote.css('span.text::text').extract_first(),
|
|
'author': quote.xpath('span/small/text()').extract_first(),
|
|
}
|
|
|
|
next_page = response.css('li.next a::attr("href")').extract_first()
|
|
if next_page is not None:
|
|
yield response.follow(next_page, self.parse)
|